National Health and Nutrition Examination Survey, 2017–March 2020 Prepandemic File: Sample Design, Estimation, and Analytic Guidelines

ABSTRACT

Background The National Health and Nutrition Examination Survey (NHANES) produces national estimates that are representative of the total noninstitutionalized civilian U.S. population. The NHANES sample is selected using a complex, four-stage sample design. NHANES sample weights are used by analysts to produce estimates of the health statistics that would have been obtained if the entire sampling frame (the noninstitutionalized civilian U.S. population) had been surveyed. Sampling errors should be calculated for all survey estimates to assess their statistical reliability. Variance approximation procedures are required to provide reasonable, approximately unbiased, and design-consistent variance estimates for complex sample surveys like NHANES. The 2017–March 2020 files represent a unique public-use data release from NHANES. The coronavirus disease 2019 (COVID-19) pandemic required suspension of data collection in March 2020. As a result, the partially completed NHANES 2019–2020 cycle was not nationally representative. Therefore, the 2019–March 2020 data were combined with the data from the 2017–2018 cycle to create the nationally representative 2017–March 2020 prepandemic data files. Objective This report describes the creation of the NHANES 2017–March 2020 prepandemic data files, including the selection of the appropriate NHANES sample design (2015–2018) to create sample weights and variance units for public-use data files. Additionally, the development of a factor applied to the primary sampling units to adjust the 2017–March 2020 data to fit the NHANES 2015–2018 sample design is described. Analyses to assess representativeness of the target population were performed, and a simulation to replicate the impact of interrupted data collection using earlier NHANES cycles was undertaken. Analytic guidance specific to use for prepandemic data files is also included. © 2022, National Center for Health Statistics. All rights reserved.